© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14002
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon specific to scientific or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows verbs of action or problem solving

    np_acts-logits-general · gemini-2.0-flash

    defining aspects and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.70
    homonymie
    -0.65
     ujednoznacz
    -0.63
    rungsseite
    -0.63
     tartalomajánló
    -0.62
     disambiguazione
    -0.61
     AssemblyProduct
    -0.59
     kasarigan
    -0.57
    EFIAPI
    -0.56
    mappedBy
    -0.55
    POSITIVE LOGITS
     everything
    1.18
     features
    1.08
    everything
    1.07
    各项
    0.96
     key
    0.96
     elements
    0.96
     niektor
    0.92
    Основные
    0.91
     aspects
    0.90
     certaines
    0.90
    Activations Density 0.817%

    No Known Activations